Counting grapes with Computer Vision

Photo courtesy of Carnegie Mellon
Photo courtesy of Carnegie Mellon
It’s not secret that Computer Vision is an asset in the agricultural world, yet it’s still interesting to discover the new ways in which it is being put to you. For example, researchers at Carnegie Mellon University‚Äôs Robotics Institute published a study demonstrating how visual counting – one of the elementary Computer Vision concepts – is a way of estimating the yield of a crop of grapes.

Using an HD camera, a special lighting system, and a laser scanner, the setup can count grapes as small as 4mm in diameter, and using algorithms, is able to use the number of grapes and convert that to an estimated harvest yield. And while the margin of error is 9.8 percent, in humans, it’s 30, demonstrating that the Computer Vision system is more efficient and possibly more cost-effective.

ComputerVision makes strides in agricultural industry

While scientists at the Valencian Institute of Agrarian Research (IVIA) in Spain have been using computer vision to examine oranges, researchers further North at the National Physical Laboratory
(NPL) in the United Kingdom have been doing the same thing, but with strawberries.

What began in 2009 as an experiment in identifying the ripeness of cauliflower has extended to strawberries, because they are time-consuming to sort out and pick by hand.

The technology is beneficial to farmers, who, in the past, have lost money from harvesting unripe fruits and vegetables. It uses radio frequencies, microwaves, terahertz and the far-infra red to penetrate the fruit without damaging it, and determine whether or not it’s ready to be taken from the vine.

The hope is that those in the agricultural industry will be able to benefit by saving both money and time, but it will be interesting to see how else this technology can be applied.

Artificial vision separates the good from the bad

Scientists at the Valencian Institute of Agrarian Research (IVIA) have created a new way of using artificial vision to separate the good from the bad – fruit, that is.

Testing out its prototype on citrus fruits, the researchers at IVIA use computer vision to identify the quality of oranges. The technology is able to sort out which fruits are rotten and which are not. An additional machine sorts the surviving fruit by color, quality, and exterior damage at a rate of up to 20 oranges per second, classifying it as excellent or acceptable in quality. This, in turn, helps determine the markets the fruit will be sent to and the prices it will demand. A third and final machine works in the field, assisting fruit pickers in establishing which fruit is ripe and ready to be harvested.

Image courtesy of IVIA

Currently, the greatest obstacle standing in the way of this technology becoming mainstream is the cost.